Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Adaptive Neuro-Symbolic Planning for bio-inspired soft robotics maintenance in hybrid quantum-classical pipelines

Описание и применение

Нейро‑символьная система планирует обслуживание гибких роботов, учитывая непрерывные сигналы деградации и неопределённость, используя вероятностные предикаты и квантовый оптимизатор.

Задача

Soft robotic actuators degrade gradually, producing continuous degradation signals that classical symbolic planners cannot model; maintenance planning under uncertainty is the bottleneck.

Результат

The neuro‑symbolic architecture enabled maintenance planning that explicitly handled uncertainty, allowed policy adjustment via threshold tuning, and leveraged quantum annealing for large actuator sets.

Рабочий процесс

  • Collect continuous sensor data from actuators
  • Feed sensor windows into a neural network (PredicateGrounder) to obtain sigmoid probabilities for predicates such as degraded, near_failure, nominal and a health embedding
  • Pass probabilistic predicates and health scores to a MaintenanceSymbolicPlanner
  • Generate feasible action sets by ranking actuators by risk reduction per unit cost and pruning via CP‑SAT style constraints
  • Select optimal maintenance actions within budget and horizon
  • Execute maintenance actions and update sensor data
  • Iterate the loop

Доказательства

Soft actuators lose 2-3% of its force output per thousand cycles due to elastomer fatigue

Источник

The symbolic planner receives predicate probabilities, not booleans

Источник

  • Дата записи: 2026-10-10T16:40:51.036Z